Guardrail categories This topic provides an overview of the three different categories of guardrails available in the Configure Guardrails window. Content filters in GuardrailsContent filters in Guardrails enable deterministic text pattern identification using Microsoft Presidio and Python regular expressions without requiring an LLM callLLM judge in GuardrailsLLM Judge uses a second LLM, the judge model to evaluate content against a scored set of criteria. Custom GuardrailCreate custom Python functions for pre-call and post-call filtering to identify and restrict specific patterns or data typesParent topic: Guardrails in Agent Studio
